Reinforcement learning methods to handle actions with differing costs in MDPs

被引：0

作者：

Ishiguro, T ^{[1
]}

Matsui, T ^{[1
]}

Inuzuka, N ^{[1
]}

Wada, K ^{[1
]}

机构：

[1] Nagoya Inst Technol, Showa Ku, Nagoya, Aichi 4668555, Japan

来源：

KNOWLEDGE-BASED INTELLIGNET INFORMATION AND ENGINEERING SYSTEMS, PT 2, PROCEEDINGS | 2003年 / 2774卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Reinforcement learning methods for environment including actions with differing costs are investigated. Through experiments we examined treatment of this problem with Q-learning, R-learning and Profit sharing. Profit sharing with a credit assignment functions considering costs is shown to have good performance in a practical sense.

引用

页码：553 / 560

页数：8

共 50 条

[1] Reinforcement learning for MDPs with constraints
Geibel, Peter
[J]. MACHINE LEARNING: ECML 2006, PROCEEDINGS, 2006, 4212 : 646 - 653
[2] Efficient reinforcement learning in factored MDPs
Kearns, M
Koller, D
[J]. IJCAI-99: PROCEEDINGS OF THE SIXTEENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 & 2, 1999, : 740 - 747
[3] Multitask reinforcement learning on the distribution of MDPs
Tanaka, F
Yamamura, M
[J]. 2003 IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN ROBOTICS AND AUTOMATION, VOLS I-III, PROCEEDINGS, 2003, : 1108 - 1113
[4] Inverse reinforcement learning in contextual MDPs
Belogolovsky, Stav
Korsunsky, Philip
Mannor, Shie
Tessler, Chen
Zahavy, Tom
[J]. MACHINE LEARNING, 2021, 110 (09) : 2295 - 2334
[5] Inverse reinforcement learning in contextual MDPs
Stav Belogolovsky
Philip Korsunsky
Shie Mannor
Chen Tessler
Tom Zahavy
[J]. Machine Learning, 2021, 110 : 2295 - 2334
[6] Reinforcement learning in finite MDPs: PAC analysis
Strehl, Alexander L.
Li, Hong
Littman, Michael L.
[J]. Journal of Machine Learning Research, 2009, 10 : 2413 - 2444
[7] Knowledge Revision for Reinforcement Learning with Abstract MDPs
Efthymiadis, Kyriakos
Devlin, Sam
Kudenko, Daniel
[J]. AAMAS'14: PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS, 2014, : 1535 - 1536
[8] Knowledge Revision for Reinforcement Learning with Abstract MDPs
Efthymiadis, Kyriakos
Kudenko, Daniel
[J]. PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS (AAMAS'15), 2015, : 763 - 770
[9] Reinforcement Learning in Parametric MDPs with Exponential Families
Chowdhury, Sayak Ray
Gopalan, Aditya
Maillard, Odalric-Ambrym
[J]. 24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
[10] Reinforcement Learning in Finite MDPs: PAC Analysis
Strehl, Alexander L.
Li, Lihong
Littman, Michael L.
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2009, 10 : 2413 - 2444

← 1 2 3 4 5 →